Merge branch 'for-6.15/amd_sfh' into for-linus

From: Mario Limonciello <mario.limonciello@amd.com>

Some platforms include a human presence detection (HPD) sensor. When
enabled and a user is detected a wake event will be emitted from the
sensor fusion hub that software can react to.

Example use cases are "wake from suspend on approach" or to "lock
when leaving".

This is currently enabled by default on supported systems, but users
can't control it. This essentially means that wake on approach is
enabled which is a really surprising behavior to users that don't
expect it.

Instead of defaulting to enabled add a sysfs knob that users can
use to enable the feature if desirable and set it to disabled by
default.

1 files changed, 168 insertions, 248 deletions

diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index ce8886122ed3..0e4c805e7e89 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -3,7 +3,8 @@
  * Debug and Guest Debug support
  *
  * Copyright (C) 2015 - Linaro Ltd
- * Author: Alex Bennée <alex.bennee@linaro.org>
+ * Authors: Alex Bennée <alex.bennee@linaro.org>
+ * 	    Oliver Upton <oliver.upton@linux.dev>
  */
 
 #include <linux/kvm_host.h>
@@ -14,72 +15,6 @@
 #include <asm/kvm_arm.h>
 #include <asm/kvm_emulate.h>
 
-#include "trace.h"
-
-/* These are the bits of MDSCR_EL1 we may manipulate */
-#define MDSCR_EL1_DEBUG_MASK	(DBG_MDSCR_SS | \
-				DBG_MDSCR_KDE | \
-				DBG_MDSCR_MDE)
-
-static DEFINE_PER_CPU(u64, mdcr_el2);
-
-/*
- * save/restore_guest_debug_regs
- *
- * For some debug operations we need to tweak some guest registers. As
- * a result we need to save the state of those registers before we
- * make those modifications.
- *
- * Guest access to MDSCR_EL1 is trapped by the hypervisor and handled
- * after we have restored the preserved value to the main context.
- *
- * When single-step is enabled by userspace, we tweak PSTATE.SS on every
- * guest entry. Preserve PSTATE.SS so we can restore the original value
- * for the vcpu after the single-step is disabled.
- */
-static void save_guest_debug_regs(struct kvm_vcpu *vcpu)
-{
-	u64 val = vcpu_read_sys_reg(vcpu, MDSCR_EL1);
-
-	vcpu->arch.guest_debug_preserved.mdscr_el1 = val;
-
-	trace_kvm_arm_set_dreg32("Saved MDSCR_EL1",
-				vcpu->arch.guest_debug_preserved.mdscr_el1);
-
-	vcpu->arch.guest_debug_preserved.pstate_ss =
-					(*vcpu_cpsr(vcpu) & DBG_SPSR_SS);
-}
-
-static void restore_guest_debug_regs(struct kvm_vcpu *vcpu)
-{
-	u64 val = vcpu->arch.guest_debug_preserved.mdscr_el1;
-
-	vcpu_write_sys_reg(vcpu, val, MDSCR_EL1);
-
-	trace_kvm_arm_set_dreg32("Restored MDSCR_EL1",
-				vcpu_read_sys_reg(vcpu, MDSCR_EL1));
-
-	if (vcpu->arch.guest_debug_preserved.pstate_ss)
-		*vcpu_cpsr(vcpu) |= DBG_SPSR_SS;
-	else
-		*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
-}
-
-/**
- * kvm_arm_init_debug - grab what we need for debug
- *
- * Currently the sole task of this function is to retrieve the initial
- * value of mdcr_el2 so we can preserve MDCR_EL2.HPMN which has
- * presumably been set-up by some knowledgeable bootcode.
- *
- * It is called once per-cpu during CPU hyp initialisation.
- */
-
-void kvm_arm_init_debug(void)
-{
-	__this_cpu_write(mdcr_el2, kvm_call_hyp_ret(__kvm_get_mdcr_el2));
-}
-
 /**
  * kvm_arm_setup_mdcr_el2 - configure vcpu mdcr_el2 value
  *
@@ -95,11 +30,14 @@ void kvm_arm_init_debug(void)
  */
 static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu)
 {
+	preempt_disable();
+
 	/*
 	 * This also clears MDCR_EL2_E2PB_MASK and MDCR_EL2_E2TB_MASK
 	 * to disable guest access to the profiling and trace buffers
 	 */
-	vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK;
+	vcpu->arch.mdcr_el2 = FIELD_PREP(MDCR_EL2_HPMN,
+					 *host_data_ptr(nr_event_counters));
 	vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM |
 				MDCR_EL2_TPMS |
 				MDCR_EL2_TTRF |
@@ -113,233 +51,215 @@ static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu)
 		vcpu->arch.mdcr_el2 |= MDCR_EL2_TDE;
 
 	/*
-	 * Trap debug register access when one of the following is true:
-	 *  - Userspace is using the hardware to debug the guest
-	 *  (KVM_GUESTDBG_USE_HW is set).
-	 *  - The guest is not using debug (DEBUG_DIRTY clear).
-	 *  - The guest has enabled the OS Lock (debug exceptions are blocked).
+	 * Trap debug registers if the guest doesn't have ownership of them.
 	 */
-	if ((vcpu->guest_debug & KVM_GUESTDBG_USE_HW) ||
-	    !vcpu_get_flag(vcpu, DEBUG_DIRTY) ||
-	    kvm_vcpu_os_lock_enabled(vcpu))
+	if (!kvm_guest_owns_debug_regs(vcpu))
 		vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA;
 
-	trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2);
-}
+	/* Write MDCR_EL2 directly if we're already at EL2 */
+	if (has_vhe())
+		write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
 
-/**
- * kvm_arm_vcpu_init_debug - setup vcpu debug traps
- *
- * @vcpu:	the vcpu pointer
- *
- * Set vcpu initial mdcr_el2 value.
- */
-void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu)
-{
-	preempt_disable();
-	kvm_arm_setup_mdcr_el2(vcpu);
 	preempt_enable();
 }
 
-/**
- * kvm_arm_reset_debug_ptr - reset the debug ptr to point to the vcpu state
- * @vcpu:	the vcpu pointer
- */
-
-void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu)
+void kvm_init_host_debug_data(void)
 {
-	vcpu->arch.debug_ptr = &vcpu->arch.vcpu_debug_state;
+	u64 dfr0 = read_sysreg(id_aa64dfr0_el1);
+
+	if (cpuid_feature_extract_signed_field(dfr0, ID_AA64DFR0_EL1_PMUVer_SHIFT) > 0)
+		*host_data_ptr(nr_event_counters) = FIELD_GET(ARMV8_PMU_PMCR_N,
+							      read_sysreg(pmcr_el0));
+
+	*host_data_ptr(debug_brps) = SYS_FIELD_GET(ID_AA64DFR0_EL1, BRPs, dfr0);
+	*host_data_ptr(debug_wrps) = SYS_FIELD_GET(ID_AA64DFR0_EL1, WRPs, dfr0);
+
+	if (has_vhe())
+		return;
+
+	if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_PMSVer_SHIFT) &&
+	    !(read_sysreg_s(SYS_PMBIDR_EL1) & PMBIDR_EL1_P))
+		host_data_set_flag(HAS_SPE);
+
+	if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceFilt_SHIFT)) {
+		/* Force disable trace in protected mode in case of no TRBE */
+		if (is_protected_kvm_enabled())
+			host_data_set_flag(EL1_TRACING_CONFIGURED);
+
+		if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceBuffer_SHIFT) &&
+		    !(read_sysreg_s(SYS_TRBIDR_EL1) & TRBIDR_EL1_P))
+			host_data_set_flag(HAS_TRBE);
+	}
 }
 
-/**
- * kvm_arm_setup_debug - set up debug related stuff
+/*
+ * Configures the 'external' MDSCR_EL1 value for the guest, i.e. when the host
+ * has taken over MDSCR_EL1.
  *
- * @vcpu:	the vcpu pointer
+ *  - Userspace is single-stepping the guest, and MDSCR_EL1.SS is forced to 1.
  *
- * This is called before each entry into the hypervisor to setup any
- * debug related registers.
+ *  - Userspace is using the breakpoint/watchpoint registers to debug the
+ *    guest, and MDSCR_EL1.MDE is forced to 1.
  *
- * Additionally, KVM only traps guest accesses to the debug registers if
- * the guest is not actively using them (see the DEBUG_DIRTY
- * flag on vcpu->arch.iflags).  Since the guest must not interfere
- * with the hardware state when debugging the guest, we must ensure that
- * trapping is enabled whenever we are debugging the guest using the
- * debug registers.
+ *  - The guest has enabled the OS Lock, and KVM is forcing MDSCR_EL1.MDE to 0,
+ *    masking all debug exceptions affected by the OS Lock.
  */
-
-void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
+static void setup_external_mdscr(struct kvm_vcpu *vcpu)
 {
-	unsigned long mdscr, orig_mdcr_el2 = vcpu->arch.mdcr_el2;
+	/*
+	 * Use the guest's MDSCR_EL1 as a starting point, since there are
+	 * several other features controlled by MDSCR_EL1 that are not relevant
+	 * to the host.
+	 *
+	 * Clear the bits that KVM may use which also satisfies emulation of
+	 * the OS Lock as MDSCR_EL1.MDE is cleared.
+	 */
+	u64 mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1) & ~(MDSCR_EL1_SS |
+							   MDSCR_EL1_MDE |
+							   MDSCR_EL1_KDE);
 
-	trace_kvm_arm_setup_debug(vcpu, vcpu->guest_debug);
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		mdscr |= MDSCR_EL1_SS;
 
-	kvm_arm_setup_mdcr_el2(vcpu);
+	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW)
+		mdscr |= MDSCR_EL1_MDE | MDSCR_EL1_KDE;
 
-	/* Check if we need to use the debug registers. */
+	vcpu->arch.external_mdscr_el1 = mdscr;
+}
+
+void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu)
+{
+	u64 mdscr;
+
+	/* Must be called before kvm_vcpu_load_vhe() */
+	KVM_BUG_ON(vcpu_get_flag(vcpu, SYSREGS_ON_CPU), vcpu->kvm);
+
+	/*
+	 * Determine which of the possible debug states we're in:
+	 *
+	 *  - VCPU_DEBUG_HOST_OWNED: KVM has taken ownership of the guest's
+	 *    breakpoint/watchpoint registers, or needs to use MDSCR_EL1 to do
+	 *    software step or emulate the effects of the OS Lock being enabled.
+	 *
+	 *  - VCPU_DEBUG_GUEST_OWNED: The guest has debug exceptions enabled, and
+	 *    the breakpoint/watchpoint registers need to be loaded eagerly.
+	 *
+	 *  - VCPU_DEBUG_FREE: Neither of the above apply, no breakpoint/watchpoint
+	 *    context needs to be loaded on the CPU.
+	 */
 	if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) {
-		/* Save guest debug state */
-		save_guest_debug_regs(vcpu);
+		vcpu->arch.debug_owner = VCPU_DEBUG_HOST_OWNED;
+		setup_external_mdscr(vcpu);
 
 		/*
-		 * Single Step (ARM ARM D2.12.3 The software step state
-		 * machine)
-		 *
-		 * If we are doing Single Step we need to manipulate
-		 * the guest's MDSCR_EL1.SS and PSTATE.SS. Once the
-		 * step has occurred the hypervisor will trap the
-		 * debug exception and we return to userspace.
-		 *
-		 * If the guest attempts to single step its userspace
-		 * we would have to deal with a trapped exception
-		 * while in the guest kernel. Because this would be
-		 * hard to unwind we suppress the guest's ability to
-		 * do so by masking MDSCR_EL.SS.
-		 *
-		 * This confuses guest debuggers which use
-		 * single-step behind the scenes but everything
-		 * returns to normal once the host is no longer
-		 * debugging the system.
+		 * Steal the guest's single-step state machine if userspace wants
+		 * single-step the guest.
 		 */
 		if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
-			/*
-			 * If the software step state at the last guest exit
-			 * was Active-pending, we don't set DBG_SPSR_SS so
-			 * that the state is maintained (to not run another
-			 * single-step until the pending Software Step
-			 * exception is taken).
-			 */
-			if (!vcpu_get_flag(vcpu, DBG_SS_ACTIVE_PENDING))
+			if (*vcpu_cpsr(vcpu) & DBG_SPSR_SS)
+				vcpu_clear_flag(vcpu, GUEST_SS_ACTIVE_PENDING);
+			else
+				vcpu_set_flag(vcpu, GUEST_SS_ACTIVE_PENDING);
+
+			if (!vcpu_get_flag(vcpu, HOST_SS_ACTIVE_PENDING))
 				*vcpu_cpsr(vcpu) |= DBG_SPSR_SS;
 			else
 				*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
-
-			mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1);
-			mdscr |= DBG_MDSCR_SS;
-			vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1);
-		} else {
-			mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1);
-			mdscr &= ~DBG_MDSCR_SS;
-			vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1);
 		}
+	} else {
+		mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1);
 
-		trace_kvm_arm_set_dreg32("SPSR_EL2", *vcpu_cpsr(vcpu));
-
-		/*
-		 * HW Breakpoints and watchpoints
-		 *
-		 * We simply switch the debug_ptr to point to our new
-		 * external_debug_state which has been populated by the
-		 * debug ioctl. The existing DEBUG_DIRTY mechanism ensures
-		 * the registers are updated on the world switch.
-		 */
-		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) {
-			/* Enable breakpoints/watchpoints */
-			mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1);
-			mdscr |= DBG_MDSCR_MDE;
-			vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1);
-
-			vcpu->arch.debug_ptr = &vcpu->arch.external_debug_state;
-			vcpu_set_flag(vcpu, DEBUG_DIRTY);
-
-			trace_kvm_arm_set_regset("BKPTS", get_num_brps(),
-						&vcpu->arch.debug_ptr->dbg_bcr[0],
-						&vcpu->arch.debug_ptr->dbg_bvr[0]);
-
-			trace_kvm_arm_set_regset("WAPTS", get_num_wrps(),
-						&vcpu->arch.debug_ptr->dbg_wcr[0],
-						&vcpu->arch.debug_ptr->dbg_wvr[0]);
-
-		/*
-		 * The OS Lock blocks debug exceptions in all ELs when it is
-		 * enabled. If the guest has enabled the OS Lock, constrain its
-		 * effects to the guest. Emulate the behavior by clearing
-		 * MDSCR_EL1.MDE. In so doing, we ensure that host debug
-		 * exceptions are unaffected by guest configuration of the OS
-		 * Lock.
-		 */
-		} else if (kvm_vcpu_os_lock_enabled(vcpu)) {
-			mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1);
-			mdscr &= ~DBG_MDSCR_MDE;
-			vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1);
-		}
+		if (mdscr & (MDSCR_EL1_KDE | MDSCR_EL1_MDE))
+			vcpu->arch.debug_owner = VCPU_DEBUG_GUEST_OWNED;
+		else
+			vcpu->arch.debug_owner = VCPU_DEBUG_FREE;
 	}
 
-	BUG_ON(!vcpu->guest_debug &&
-		vcpu->arch.debug_ptr != &vcpu->arch.vcpu_debug_state);
-
-	/* If KDE or MDE are set, perform a full save/restore cycle. */
-	if (vcpu_read_sys_reg(vcpu, MDSCR_EL1) & (DBG_MDSCR_KDE | DBG_MDSCR_MDE))
-		vcpu_set_flag(vcpu, DEBUG_DIRTY);
-
-	/* Write mdcr_el2 changes since vcpu_load on VHE systems */
-	if (has_vhe() && orig_mdcr_el2 != vcpu->arch.mdcr_el2)
-		write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
-
-	trace_kvm_arm_set_dreg32("MDSCR_EL1", vcpu_read_sys_reg(vcpu, MDSCR_EL1));
+	kvm_arm_setup_mdcr_el2(vcpu);
 }
 
-void kvm_arm_clear_debug(struct kvm_vcpu *vcpu)
+void kvm_vcpu_put_debug(struct kvm_vcpu *vcpu)
 {
-	trace_kvm_arm_clear_debug(vcpu->guest_debug);
+	if (likely(!(vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
+		return;
 
 	/*
-	 * Restore the guest's debug registers if we were using them.
+	 * Save the host's software step state and restore the guest's before
+	 * potentially returning to userspace.
 	 */
-	if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) {
-		if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
-			if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS))
-				/*
-				 * Mark the vcpu as ACTIVE_PENDING
-				 * until Software Step exception is taken.
-				 */
-				vcpu_set_flag(vcpu, DBG_SS_ACTIVE_PENDING);
-		}
-
-		restore_guest_debug_regs(vcpu);
+	if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS))
+		vcpu_set_flag(vcpu, HOST_SS_ACTIVE_PENDING);
+	else
+		vcpu_clear_flag(vcpu, HOST_SS_ACTIVE_PENDING);
 
-		/*
-		 * If we were using HW debug we need to restore the
-		 * debug_ptr to the guest debug state.
-		 */
-		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) {
-			kvm_arm_reset_debug_ptr(vcpu);
+	if (vcpu_get_flag(vcpu, GUEST_SS_ACTIVE_PENDING))
+		*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
+	else
+		*vcpu_cpsr(vcpu) |= DBG_SPSR_SS;
+}
 
-			trace_kvm_arm_set_regset("BKPTS", get_num_brps(),
-						&vcpu->arch.debug_ptr->dbg_bcr[0],
-						&vcpu->arch.debug_ptr->dbg_bvr[0]);
+/*
+ * Updates ownership of the debug registers after a trapped guest access to a
+ * breakpoint/watchpoint register. Host ownership of the debug registers is of
+ * strictly higher priority, and it is the responsibility of the VMM to emulate
+ * guest debug exceptions in this configuration.
+ */
+void kvm_debug_set_guest_ownership(struct kvm_vcpu *vcpu)
+{
+	if (kvm_host_owns_debug_regs(vcpu))
+		return;
 
-			trace_kvm_arm_set_regset("WAPTS", get_num_wrps(),
-						&vcpu->arch.debug_ptr->dbg_wcr[0],
-						&vcpu->arch.debug_ptr->dbg_wvr[0]);
-		}
-	}
+	vcpu->arch.debug_owner = VCPU_DEBUG_GUEST_OWNED;
+	kvm_arm_setup_mdcr_el2(vcpu);
 }
 
-void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu)
+void kvm_debug_handle_oslar(struct kvm_vcpu *vcpu, u64 val)
 {
-	u64 dfr0;
+	if (val & OSLAR_EL1_OSLK)
+		__vcpu_sys_reg(vcpu, OSLSR_EL1) |= OSLSR_EL1_OSLK;
+	else
+		__vcpu_sys_reg(vcpu, OSLSR_EL1) &= ~OSLSR_EL1_OSLK;
 
-	/* For VHE, there is nothing to do */
-	if (has_vhe())
+	preempt_disable();
+	kvm_arch_vcpu_put(vcpu);
+	kvm_arch_vcpu_load(vcpu, smp_processor_id());
+	preempt_enable();
+}
+
+void kvm_enable_trbe(void)
+{
+	if (has_vhe() || is_protected_kvm_enabled() ||
+	    WARN_ON_ONCE(preemptible()))
 		return;
 
-	dfr0 = read_sysreg(id_aa64dfr0_el1);
-	/*
-	 * If SPE is present on this CPU and is available at current EL,
-	 * we may need to check if the host state needs to be saved.
-	 */
-	if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_PMSVer_SHIFT) &&
-	    !(read_sysreg_s(SYS_PMBIDR_EL1) & BIT(PMBIDR_EL1_P_SHIFT)))
-		vcpu_set_flag(vcpu, DEBUG_STATE_SAVE_SPE);
+	host_data_set_flag(TRBE_ENABLED);
+}
+EXPORT_SYMBOL_GPL(kvm_enable_trbe);
+
+void kvm_disable_trbe(void)
+{
+	if (has_vhe() || is_protected_kvm_enabled() ||
+	    WARN_ON_ONCE(preemptible()))
+		return;
 
-	/* Check if we have TRBE implemented and available at the host */
-	if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceBuffer_SHIFT) &&
-	    !(read_sysreg_s(SYS_TRBIDR_EL1) & TRBIDR_EL1_P))
-		vcpu_set_flag(vcpu, DEBUG_STATE_SAVE_TRBE);
+	host_data_clear_flag(TRBE_ENABLED);
 }
+EXPORT_SYMBOL_GPL(kvm_disable_trbe);
 
-void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu)
+void kvm_tracing_set_el1_configuration(u64 trfcr_while_in_guest)
 {
-	vcpu_clear_flag(vcpu, DEBUG_STATE_SAVE_SPE);
-	vcpu_clear_flag(vcpu, DEBUG_STATE_SAVE_TRBE);
+	if (is_protected_kvm_enabled() || WARN_ON_ONCE(preemptible()))
+		return;
+
+	if (has_vhe()) {
+		write_sysreg_s(trfcr_while_in_guest, SYS_TRFCR_EL12);
+		return;
+	}
+
+	*host_data_ptr(trfcr_while_in_guest) = trfcr_while_in_guest;
+	if (read_sysreg_s(SYS_TRFCR_EL1) != trfcr_while_in_guest)
+		host_data_set_flag(EL1_TRACING_CONFIGURED);
+	else
+		host_data_clear_flag(EL1_TRACING_CONFIGURED);
 }
+EXPORT_SYMBOL_GPL(kvm_tracing_set_el1_configuration);